Optimizing the performance of reactive molecular dynamics simulations for many-core architectures
Abstract
Reactive molecular dynamics simulations are computationally demanding. Reaching spatial and temporal scales where interesting scientific phenomena can be observed requires efficient and scalable implementations on modern hardware. In this article, we focus on optimizing the performance of the widely used LAMMPS/ReaxC package for many-core architectures. As hybrid parallelism allows better leverage of the increasing on-node parallelism, we adopt thread parallelism in the construction of bonded and nonbonded lists and in the computation of complex ReaxFF interactions. To mitigate the I/O overheads due to large volumes of trajectory data produced and to save users the burden of post-processing, we also develop a novel in situ tool for molecular species analysis. We analyze the performance of the resulting ReaxC-OMP package on two different architectures: (i) Mira, an IBM Blue Gene/Q system and (ii) Cori-II, a Cray XC-40 sytem with Knights Landing processors. For Pentaerythritol tetranitrate (PETN) systems of sizes ranging from 32 thousand to 16.6 million particles, we observe speedups in the range of 1.5-4.5x. We observe sustained performance improvements for up to 262,144 cores (1,048,576 processes) of Mira and a weak scaling efficiency of 91.5% in large simulations containing 16.6 million particles. Finally, the in situ molecular species analysis tool incursmore »
- Authors:
-
- Michigan State Univ., East Lansing, MI (United States). Dept. of Computer Science and Engineering; Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Computational Research Division
- Argonne National Lab. (ANL), Argonne, IL (United States). Argonne Leadership Computing Facility
- Michigan State Univ., East Lansing, MI (United States). Dept. of Computer Science and Engineering
- Sandia National Lab. (SNL-CA), Livermore, CA (United States). Multiscale Science Dept.
- Publication Date:
- Research Org.:
- Argonne National Lab. (ANL), Argonne, IL (United States)
- Sponsoring Org.:
- Argonne National Laboratory (ANL), Argonne, IL (United States). Argonne Leadership Computing Facility
- OSTI Identifier:
- 1530430
- Grant/Contract Number:
- AC02-06CH11357
- Resource Type:
- Accepted Manuscript
- Journal Name:
- International Journal of High Performance Computing Applications
- Additional Journal Information:
- Journal Volume: 33; Journal Issue: 2; Journal ID: ISSN 1094-3420
- Publisher:
- SAGE
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; hybrid MPI/OpenMP parallelism; LAMMPS-ReaxC-OMP; multi-core architectures; reactive molecular dynamics; ReaxFF; many-core architectures
Citation Formats
Aktulga, Hasan Metin, Knight, Chris, Coffman, Paul, O’Hearn, Kurt A., Shan, Tzu-Ray, and Jiang, Wei. Optimizing the performance of reactive molecular dynamics simulations for many-core architectures. United States: N. p., 2018.
Web. doi:10.1177/1094342017746221.
Aktulga, Hasan Metin, Knight, Chris, Coffman, Paul, O’Hearn, Kurt A., Shan, Tzu-Ray, & Jiang, Wei. Optimizing the performance of reactive molecular dynamics simulations for many-core architectures. United States. https://doi.org/10.1177/1094342017746221
Aktulga, Hasan Metin, Knight, Chris, Coffman, Paul, O’Hearn, Kurt A., Shan, Tzu-Ray, and Jiang, Wei. Mon .
"Optimizing the performance of reactive molecular dynamics simulations for many-core architectures". United States. https://doi.org/10.1177/1094342017746221. https://www.osti.gov/servlets/purl/1530430.
@article{osti_1530430,
title = {Optimizing the performance of reactive molecular dynamics simulations for many-core architectures},
author = {Aktulga, Hasan Metin and Knight, Chris and Coffman, Paul and O’Hearn, Kurt A. and Shan, Tzu-Ray and Jiang, Wei},
abstractNote = {Reactive molecular dynamics simulations are computationally demanding. Reaching spatial and temporal scales where interesting scientific phenomena can be observed requires efficient and scalable implementations on modern hardware. In this article, we focus on optimizing the performance of the widely used LAMMPS/ReaxC package for many-core architectures. As hybrid parallelism allows better leverage of the increasing on-node parallelism, we adopt thread parallelism in the construction of bonded and nonbonded lists and in the computation of complex ReaxFF interactions. To mitigate the I/O overheads due to large volumes of trajectory data produced and to save users the burden of post-processing, we also develop a novel in situ tool for molecular species analysis. We analyze the performance of the resulting ReaxC-OMP package on two different architectures: (i) Mira, an IBM Blue Gene/Q system and (ii) Cori-II, a Cray XC-40 sytem with Knights Landing processors. For Pentaerythritol tetranitrate (PETN) systems of sizes ranging from 32 thousand to 16.6 million particles, we observe speedups in the range of 1.5-4.5x. We observe sustained performance improvements for up to 262,144 cores (1,048,576 processes) of Mira and a weak scaling efficiency of 91.5% in large simulations containing 16.6 million particles. Finally, the in situ molecular species analysis tool incurs only insignificant overheads across various system sizes and runs configurations.},
doi = {10.1177/1094342017746221},
journal = {International Journal of High Performance Computing Applications},
number = 2,
volume = 33,
place = {United States},
year = {Mon Jan 08 00:00:00 EST 2018},
month = {Mon Jan 08 00:00:00 EST 2018}
}
Web of Science
Works referenced in this record:
General purpose molecular dynamics simulations fully implemented on graphics processing units
journal, May 2008
- Anderson, Joshua A.; Lorenz, Chris D.; Travesset, A.
- Journal of Computational Physics, Vol. 227, Issue 10
Reactive Molecular Dynamics: Numerical Methods and Algorithmic Techniques
journal, January 2012
- Aktulga, Hasan Metin; Pandit, Sagar A.; van Duin, Adri C. T.
- SIAM Journal on Scientific Computing, Vol. 34, Issue 1
GPU-accelerated molecular visualization on petascale supercomputing platforms
conference, January 2013
- Stone, John E.; Vandivort, Kirby L.; Schulten, Klaus
- Proceedings of the 8th International Workshop on Ultrascale Visualization - UltraVis '13
A Flexible Framework for Asynchronous in Situ and in Transit Analytics for Scientific Simulations
conference, May 2014
- Dreher, Matthieu; Raffin, Bruno
- 2014 14th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid)
PuReMD-GPU: A reactive molecular dynamics simulation package for GPUs
journal, September 2014
- Kylasa, S. B.; Aktulga, H. M.; Grama, A. Y.
- Journal of Computational Physics, Vol. 272
Algorithms of GPU-enabled reactive force field (ReaxFF) molecular dynamics
journal, April 2013
- Zheng, Mo; Li, Xiaoxia; Guo, Li
- Journal of Molecular Graphics and Modelling, Vol. 41
Classical atomistic simulations of surfaces and heterogeneous interfaces with the charge-optimized many body (COMB) potentials
journal, September 2013
- Liang, Tao; Shan, Tzu-Ray; Cheng, Yu-Ting
- Materials Science and Engineering: R: Reports, Vol. 74, Issue 9
The ReaxFF reactive force-field: development, applications and future directions
journal, March 2016
- Senftle, Thomas P.; Hong, Sungwook; Islam, Md Mahbubul
- npj Computational Materials, Vol. 2, Issue 1
A fast, scalable method for the parallel evaluation of distance-limited pairwise particle interactions
journal, January 2005
- Shaw, David E.
- Journal of Computational Chemistry, Vol. 26, Issue 13
GROMACS 4: Algorithms for Highly Efficient, Load-Balanced, and Scalable Molecular Simulation
journal, February 2008
- Hess, Berk; Kutzner, Carsten; van der Spoel, David
- Journal of Chemical Theory and Computation, Vol. 4, Issue 3
Charge equilibration for molecular dynamics simulations
journal, April 1991
- Rappe, Anthony K.; Goddard, William A.
- The Journal of Physical Chemistry, Vol. 95, Issue 8
Global optimization of parameters in the reactive force field ReaxFF for SiOH
journal, July 2013
- Larsson, Henrik R.; van Duin, Adri C. T.; Hartke, Bernd
- Journal of Computational Chemistry, Vol. 34, Issue 25
An empirical valence bond approach for comparing reactions in solutions and in enzymes
journal, September 1980
- Warshel, Arieh; Weiss, Robert M.
- Journal of the American Chemical Society, Vol. 102, Issue 20
Macroscale superlubricity enabled by graphene nanoscroll formation
journal, May 2015
- Berman, D.; Deshmukh, S. A.; Sankaranarayanan, S. K. R. S.
- Science, Vol. 348, Issue 6239
Dynamic topology aware load balancing algorithms for molecular dynamics applications
conference, January 2009
- Bhatelé, Abhinav; Kalé, Laxmikant V.; Kumar, Sameer
- Proceedings of the 23rd international conference on Conference on Supercomputing - ICS '09
Fast Parallel Algorithms for Short-Range Molecular Dynamics
journal, March 1995
- Plimpton, Steve
- Journal of Computational Physics, Vol. 117, Issue 1
A reactive potential for hydrocarbons with intermolecular interactions
journal, April 2000
- Stuart, Steven J.; Tutein, Alan B.; Harrison, Judith A.
- The Journal of Chemical Physics, Vol. 112, Issue 14
Analysis of scalable data-privatization threading algorithms for hybrid MPI/OpenMP parallelization of molecular dynamics
journal, April 2013
- Kunaseth, Manaschai; Richards, David F.; Glosli, James N.
- The Journal of Supercomputing, Vol. 66, Issue 1
ReaxFF: A Reactive Force Field for Hydrocarbons
journal, October 2001
- van Duin, Adri C. T.; Dasgupta, Siddharth; Lorant, Francois
- The Journal of Physical Chemistry A, Vol. 105, Issue 41
Exploiting hierarchy parallelism for molecular dynamics on a petascale heterogeneous system
journal, December 2013
- Wu, Qiang; Yang, Canqun; Tang, Tao
- Journal of Parallel and Distributed Computing, Vol. 73, Issue 12
Parallel Optimization of a Reactive Force Field for Polycondensation of Alkoxysilanes
journal, September 2014
- Deetz, Joshua D.; Faller, Roland
- The Journal of Physical Chemistry B, Vol. 118, Issue 37
The OPLS [optimized potentials for liquid simulations] potential functions for proteins, energy minimizations for crystals of cyclic peptides and crambin
journal, March 1988
- Jorgensen, William L.; Tirado-Rives, Julian
- Journal of the American Chemical Society, Vol. 110, Issue 6
GMRES: A Generalized Minimal Residual Algorithm for Solving Nonsymmetric Linear Systems
journal, July 1986
- Saad, Youcef; Schultz, Martin H.
- SIAM Journal on Scientific and Statistical Computing, Vol. 7, Issue 3
Exploring SIMD for Molecular Dynamics, Using Intel® Xeon® Processors and Intel® Xeon Phi Coprocessors
conference, May 2013
- Pennycook, Simon J.; Hughes, Chris J.; Smelyanskiy, M.
- 2013 IEEE International Symposium on Parallel & Distributed Processing (IPDPS), 2013 IEEE 27th International Symposium on Parallel and Distributed Processing
All-Atom Empirical Potential for Molecular Modeling and Dynamics Studies of Proteins †
journal, April 1998
- MacKerell, A. D.; Bashford, D.; Bellott, M.
- The Journal of Physical Chemistry B, Vol. 102, Issue 18
Parallel reactive molecular dynamics: Numerical methods and algorithmic techniques
journal, April 2012
- Aktulga, H. M.; Fogarty, J. C.; Pandit, S. A.
- Parallel Computing, Vol. 38, Issue 4-5
Electronegativity-equalization method for the calculation of atomic charges in molecules
journal, July 1986
- Mortier, Wilfried J.; Ghosh, Swapan K.; Shankar, S.
- Journal of the American Chemical Society, Vol. 108, Issue 15
A Second Generation Force Field for the Simulation of Proteins, Nucleic Acids, and Organic Molecules
journal, May 1995
- Cornell, Wendy D.; Cieplak, Piotr; Bayly, Christopher I.
- Journal of the American Chemical Society, Vol. 117, Issue 19
A scalable parallel algorithm for large-scale reactive force-field molecular dynamics simulations
journal, January 2008
- Nomura, Ken-ichi; Kalia, Rajiv K.; Nakano, Aiichiro
- Computer Physics Communications, Vol. 178, Issue 2
General Multiobjective Force Field Optimization Framework, with Application to Reactive Force Fields for Silicon Carbide
journal, March 2014
- Jaramillo-Botero, Andres; Naserifar, Saber; Goddard, William A.
- Journal of Chemical Theory and Computation, Vol. 10, Issue 4
In-Situ Feature Extraction of Large Scale Combustion Simulations Using Segmented Merge Trees
conference, November 2014
- Landge, Aaditya G.; Pascucci, Valerio; Gyulassy, Attila
- SC14: International Conference for High Performance Computing, Networking, Storage and Analysis
Damaris/Viz: A nonintrusive, adaptable and user-friendly in situ visualization framework
conference, October 2013
- Dorier, Matthieu; Sisneros, Robert; Peterka, Tom
- 2013 IEEE Symposium on Large-Scale Data Analysis and Visualization (LDAV)
Methods of conjugate gradients for solving linear systems
journal, December 1952
- Hestenes, M. R.; Stiefel, E.
- Journal of Research of the National Bureau of Standards, Vol. 49, Issue 6
The Curious Case of the Hydrated Proton
journal, August 2011
- Knight, Chris; Voth, Gregory A.
- Accounts of Chemical Research, Vol. 45, Issue 1
A divide-and-conquer/cellular-decomposition framework for million-to-billion atom simulations of chemical reactions
journal, February 2007
- Nakano, Aiichiro; Kalia, Rajiv K.; Nomura, Ken-ichi
- Computational Materials Science, Vol. 38, Issue 4
Zonal methods for the parallel execution of range-limited N-body simulations
journal, January 2007
- Bowers, Kevin J.; Dror, Ron O.; Shaw, David E.
- Journal of Computational Physics, Vol. 221, Issue 1
Works referencing / citing this record:
Inertial extended-Lagrangian scheme for solving charge equilibration models
journal, January 2019
- Leven, Itai; Head-Gordon, Teresa
- Physical Chemistry Chemical Physics, Vol. 21, Issue 34
Inertial Extended-Lagrangian Scheme for Solving Charge Equilibration Models
text, January 2019
- Leven, Itai; Head-Gordon, Teresa
- arXiv